Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words followed by specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lon
    0.41
     国
    0.40
    Graphic
    0.39
    iverr
    0.39
    graphics
    0.39
    ijing
    0.39
    ամ
    0.39
    の結果
    0.38
    我国
    0.38
    өн
    0.38
    POSITIVE LOGITS
    pé
    0.44
    累積
    0.39
     Flex
    0.39
     corretamente
    0.38
     kosher
    0.38
     venit
    0.37
     bestand
    0.37
     అందు
    0.37
     mistake
    0.36
     pecc
    0.36
    Act Density 0.000%

    No Known Activations